© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32849
    Prev
    Next
    INDEX
    Explanations

    immune deficiency syndrome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moreira
    -0.08
    æŀ¶ç©º
    -0.07
    款
    -0.07
    ovit
    -0.07
     Maia
    -0.07
    gge
    -0.07
    ingan
    -0.07
    éĽªæ¢¨
    -0.07
     sedu
    -0.07
    PLIER
    -0.07
    POSITIVE LOGITS
    -mediated
    0.08
    ä¸ĬæľĪ
    0.08
    ä¸ĵç²¾
    0.07
     sink
    0.07
    RYPT
    0.06
     mediated
    0.06
    åıijå°Ħ
    0.06
    ward
    0.06
    rypt
    0.06
    å§Ĭ
    0.06
    Activations Density 0.001%

    No Known Activations